© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 63127
    Prev
    Next
    INDEX
    Explanations

    app

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ś
    -0.08
     Profi
    -0.08
     Gathering
    -0.08
     收
    -0.08
    收
    -0.07
     collecte
    -0.07
     נק
    -0.07
     capturing
    -0.07
    Collect
    -0.07
     Carbon
    -0.07
    POSITIVE LOGITS
     permiso
    0.08
     Hubbard
    0.08
    recipes
    0.08
    )!=
    0.08
    permission
    0.08
     Heinz
    0.08
    derall
    0.08
     hath
    0.08
     Sebastián
    0.08
    857
    0.08
    Activations Density 0.002%

    No Known Activations